# Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags

arXiv: https://arxiv.org/abs/2111.00970 · HTML: https://mlsanity.com/paper/2111.00970/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [OSMnx: New Methods for Acquiring, Constructing, Analyzing, and Visualizing Complex Street Networks](https://mlsanity.com/paper/1611.01890/) (2016)
- [Tile2Vec: Unsupervised representation learning for spatially distributed data](https://mlsanity.com/paper/1805.02855/) (2018)
- [Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding](https://mlsanity.com/paper/2001.11101/) (2020)

## Built on by (most cited first, 23 of 23)

- [City Foundation Models for Learning General Purpose Representations from OpenStreetMap](https://mlsanity.com/paper/2310.00583/) (2023)
- [Road Network Representation Learning: A Dual Graph based Approach](https://mlsanity.com/paper/2304.07298/) (2023)
- [SRAI: Towards Standardization of Geospatial AI](https://mlsanity.com/paper/2310.13098/) (2023)
- [Scalable Geospatial Data Generation Using AlphaEarth Foundations Model](https://mlsanity.com/paper/2508.11739/) (2025)
- [Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics](https://mlsanity.com/paper/2403.11495/) (2024)
- [S2Vec: Self-Supervised Geospatial Embeddings for the Built Environment](https://mlsanity.com/paper/2504.16942/) (2025)
- [OBSR: Open Benchmark for Spatial Representations](https://mlsanity.com/paper/2510.05879/) (2025)
- [highway2vec -- representing OpenStreetMap microregions with respect to their road network characteristics](https://mlsanity.com/paper/2304.13865/) (2023)
- [Improving Real Estate Appraisal with POI Integration and Areal Embedding](https://mlsanity.com/paper/2311.11812/) (2023)
- [Pre-trained Transformer Uncovers Meaningful Patterns in Human Mobility Data](https://mlsanity.com/paper/2406.04029/) (2024)
- [The S2 Hierarchical Discrete Global Grid as a Nexus for Data Representation, Integration, and Querying Across Geospatial Knowledge Graphs](https://mlsanity.com/paper/2410.14808/) (2024)
- [Large-scale unsupervised spatio-temporal semantic analysis of vast regions from satellite images sequences](https://mlsanity.com/paper/2208.13504/) (2022)
- [GeoAI at ACM SIGSPATIAL: The New Frontier of Geospatial Artificial Intelligence Research](https://mlsanity.com/paper/2210.13207/) (2022)
- [Modelling the performance of delivery vehicles across urban micro-regions to accelerate the transition to cargo-bike logistics](https://mlsanity.com/paper/2301.12887/) (2023)
- [Deep autoregressive modeling for land use land cover](https://mlsanity.com/paper/2401.01395/) (2024)
- [WildGraph: Realistic Graph-based Trajectory Generation for Wildlife](https://mlsanity.com/paper/2404.08068/) (2024)
- [Urban context and delivery performance: Modelling service time for cargo bikes and vans across diverse urban environments](https://mlsanity.com/paper/2409.06730/) (2024)
- [Restoring Super-High Resolution GPS Mobility Data](https://mlsanity.com/paper/2410.12818/) (2024)
- [Discrete Gaussian Process Representations for Optimising UAV-based Precision Weed Mapping](https://mlsanity.com/paper/2503.07210/) (2025)
- [Multi-Point Proximity Encoding For Vector-Mode Geospatial Machine Learning](https://mlsanity.com/paper/2506.05016/) (2025)
- [OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs](https://mlsanity.com/paper/2606.08046/) (2026)
- [Relative Transitions, Not Absolute Destinations: A Transfer-and-Ground Framework for Target-Trajectory-Free Human Mobility Generation](https://mlsanity.com/paper/2610.02033/) (2026)
- [CartoVec: General-Purpose Location Embeddings from Open Map Data](https://mlsanity.com/paper/2610.17190/) (2026)

## Abstract (arXiv)

Representation learning of spatial and geographic data is a rapidly developing field which allows for similarity detection between areas and high-quality inference using deep neural networks. Past approaches however concentrated on embedding raster imagery (maps, street or satellite photos), mobility data or road networks. In this paper we propose the first approach to learning vector representations of OpenStreetMap regions with respect to urban functions and land-use in a micro-region grid. We identify a subset of OSM tags related to major characteristics of land-use, building and urban region functions, types of water, green or other natural areas. Through manual verification of tagging quality, we selected 36 cities were for training region representations. Uber's H3 index was used to divide the cities into hexagons, and OSM tags were aggregated for each hexagon. We propose the hex2vec method based on the Skip-gram model with negative sampling. The resulting vector representations showcase semantic structures of the map characteristics, similar to ones found in vector-based language models. We also present insights from region similarity detection in six Polish cities and propose a region typology obtained through agglomerative clustering.